US 12,406,514 B2
Generation of training materials for optical character recognition
Ali Azad, Kirkland, WA (US); and David D. Pokrajac, Everett, WA (US)
Assigned to THE BOEING COMPANY, Arlington, VA (US)
Filed by The Boeing Company, Chicago, IL (US)
Filed on May 18, 2022, as Appl. No. 17/747,584.
Prior Publication US 2023/0377360 A1, Nov. 23, 2023
Int. Cl. G06V 30/19 (2022.01); G06V 30/40 (2022.01)
CPC G06V 30/19147 (2022.01) [G06V 30/19013 (2022.01); G06V 30/19093 (2022.01); G06V 30/40 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method of generating digital training materials for optical character recognition, the method comprising:
selecting a plurality of terms that each comprise a string of characters;
for each term, generating multiple term images that are digital and that each comprises the term with a different visual appearance; positioning the term images on a background that is digital; and
generating a document that comprises the background and a plurality of the term images.